Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6115 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.7657. Min Act: -0.1700
Data Index: 7071253 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.6719. Min Act: -0.1700
Data Index: 7502426 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.4219. Min Act: -0.1700
Data Index: 7029232 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.2344. Min Act: -0.1700
Data Index: 3329505 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.1719. Min Act: -0.1700
Data Index: 157507 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.1719. Min Act: -0.1700
Data Index: 4930133 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.1094. Min Act: -0.1700
Data Index: 4977135 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.0469. Min Act: -0.1700
Data Index: 3614193 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.0782. Min Act: -0.1700
Data Index: 1704746 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.0469. Min Act: -0.1700
Data Index: 2807192 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.0469. Min Act: -0.1700
Data Index: 475626 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7657. Min Range: -6.7657
Max Act: 5.9844. Min Act: -0.1700
Data Index: 8186926 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.0469. Min Act: -0.1700
Data Index: 2145679 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.0157. Min Act: -0.1700
Data Index: 7017568 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.0157. Min Act: -0.1700
Data Index: 435325 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.0157. Min Act: -0.1700
Data Index: 7241249 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.0157. Min Act: -0.1700
Data Index: 8149950 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7657. Min Range: -6.7657
Max Act: 6.0157. Min Act: -0.1700
Data Index: 542199 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7657. Min Range: -6.7657
Max Act: 5.9219. Min Act: -0.1700
Data Index: 7004201 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7657. Min Range: -6.7657
Max Act: 5.9532. Min Act: -0.1700
Data Index: 7309666 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19